ELECTRONIC PROGRAMMING GUIDE (EPG) AFFINITY CLUSTERS

• US 20120167141A1
• Filed: 12/23/2010
• Published: 06/28/2012
• Est. Priority Date: 12/23/2010
• Status: Active Grant

• Current Assignee: Rovi Technologies Corporation (Adeia Inc.)
• Original Assignee: Microsoft Corporation
• Inventors: Arora, Gagan
• Granted Patent: US 9,204,200 B2
• Time in Patent Office: Days
• US Class Current: 725/40
• CPC Class Codes: H04N 21/4826 using recommendation lists, e.g. of programs or channels sorted out according to their score
• CPC Class Codes: H04N 21/8133 specifically related to the content, e.g. biography of the actors in a movie, detailed information about an article seen in a video program

Abstract

Techniques are described in which electronic program guide (EPG) affinity clusters may be formed based upon an assumption that programs scheduled in corresponding timeslots are targeted to the same or similar audiences. In at least some embodiments, data for an EPG is examined to identify programs that are scheduled in timeslots designated as corresponding. Metadata related to the identified programs is collected. The metadata may include titles as well as cast/crew data related to the programs. One or more affinity clusters may be formed using the collected metadata to establish relationships between actors, directors, titles and other items of the metadata. The affinity clusters may be used to provide recommendations including recommendation to view, record, or set a reminder for programs according to the relationships established by the affinity clusters.

Claims

1. A method comprising:

examining electronic programming guide (EPG) data to identify television programs scheduled in corresponding timeslots;

collecting metadata related to the identified television programs; and

forming one or more affinity clusters using the collected metadata.

2. A method as described in claim 1, wherein the one or more affinity clusters are configured to establish relationships between items of the metadata that are placed into the one or more affinity clusters.

3. A method as described in claim 1, wherein the metadata comprises data regarding cast members and crew members associated with the identified television programs and the affinity clusters are formed to establish relationships between at least some of the cast members and crew members.

4. A method as described in claim 1, wherein the corresponding timeslots include timeslots on a particular channel at a particular time in different weeks.

5. A method as described in claim 1, wherein the corresponding timeslots include timeslots on a particular channel at a particular time on different days of the week.

6. A method as described in claim 1, wherein the corresponding timeslots include timeslots on different channels at a particular time on a particular day of the week.

7. A method as described in claim 1, wherein the corresponding timeslots include linked timeslots that are linked as corresponding based upon shared audience targeting criteria.

8. A method as described in claim 1, wherein forming one or more affinity clusters using the collected metadata comprises:

ascertaining affinity values indicative of how frequently items of the collected metadata are matched in corresponding timeslots;

selecting items of the collected metadata to include in the one or more affinity clusters based upon the affinity values.

9. A method as described in claim 1, wherein forming one or more affinity clusters using the collected metadata comprises:

constructing a dissimilarity matrix to ascertain affinity values indicative of how frequently items of the collected metadata are matched in corresponding timeslots; and

comparing the affinity values to an affinity threshold configured to control which items of the collected metadata are placed into the one or more affinity clusters.

10. A method as described in claim 1, further comprising outputting a recommendation based upon the one or more affinity clusters.

11. A method comprising:

forming an affinity cluster that relates metadata describing cast and crew members associated with two television programs, one to another, based at least in part upon electronic programming guide (EPG) data indicating that the two television programs are scheduled in corresponding timeslots; and

outputting a recommendation based upon the affinity cluster to recommend programs associated with at least some of the cast and crew members described by the related metadata.

12. A method as described in claim 11, wherein the corresponding timeslots comprise timeslots on a particular channel at a particular time in different time periods.

13. A method as described in claim 11, wherein the recommendation includes one or more selectable controls configured to enable interaction with the recommended programs.

14. A method as described in claim 11, wherein forming the affinity cluster comprises:

examining the electronic programming guide (EPG) data to determine that the two television programs are scheduled in corresponding timeslots;

collecting the metadata describing the cast and crew members associated with the two television programs; and

selecting items of the collected metadata to place in the affinity cluster.

15. A method as described in claim 14, wherein selecting items of the collected metadata to place in the affinity cluster further comprises:

ascertaining affinity values indicative of how frequently items of the collected metadata are matched;

comparing the affinity values to an affinity threshold configured to control which items of the collected metadata are placed into the affinity cluster; and

selecting items of the collected metadata that satisfy the affinity threshold to place in the affinity cluster.

16. One or more computer-readable storage media comprising computer-executable instructions stored thereon that, in response to execution by one or more components of a computing system, cause the computing system to perform acts including:

examining electronic programming guide (EPG) data to identify television programs scheduled in corresponding timeslots on a particular channel at a particular time in different time periods;

configuring an affinity cluster to relate metadata describing at least cast members associated with the identified television programs one to another based upon scheduling of the programs in the corresponding timeslots; and

outputting a recommendation according to the affinity cluster to recommend programs associated with at least some of the metadata related by the affinity cluster.

17. One or more computer-readable storage media as described in claim 16, wherein the instructions further cause the computing system to perform acts including:

collecting the metadata associated with the identified television programs responsive to a determination that the television programs are scheduled in the corresponding timeslots;

placing the collected metadata in the affinity cluster to create relationships between the cast members of the identified television programs one to another; and

using the relationships between the cast members to generate the recommendation.

18. One or more computer-readable storage media as described in claim 16, wherein the instructions further cause the computing system to perform acts including:

collecting the metadata associated with the identified television programs responsive to a determination that the television programs are scheduled in the corresponding timeslots;

computing affinity values between the cast members based on the collected metadata; and

selecting cast members to relate one to another via the affinity cluster according to the computed affinity values.

19. One or more computer-readable storage media as described in claim 16, wherein the instructions further cause the computing system to perform acts including:

automatically recording at least one of the programs recommended based on the affinity cluster.

20. One or more computer-readable storage media as described in claim 16, wherein the instructions further cause the computing system to perform acts including:

automatically tuning to at least one of the programs recommended based on the affinity cluster at a scheduled time for the a least one program.